Related papers: Zero-Shot Referring Expression Comprehension via V…

Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more…

Transformer-based models have dominated natural language processing and other areas in the last few years due to their superior (zero-shot) performance on benchmark datasets. However, these models are poorly understood due to their…

Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint…

Detecting objects based on language information is a popular task that includes Open-Vocabulary object Detection (OVD) and Referring Expression Comprehension (REC). In this paper, we advance them to a more practical setting called Described…

The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward signal is notoriously difficult, as humans are often unable to…

We propose a zero-shot method for Natural Language Inference (NLI) that leverages multimodal representations by grounding language in visual contexts. Our approach generates visual representations of premises using text-to-image models and…

Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show remarkable zero-shot capabilities. In this…

We present a generic Reinforcement Learning (RL) framework optimized for crafting adversarial attacks on different model types spanning from ECG signal analysis (1D), image classification (2D), and video classification (3D). The framework…

Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation…

Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a constrained RL training framework that (i) optimizes a…

Foundation models, especially vision-language models (VLMs), offer compelling zero-shot object detection for applications like autonomous driving, a domain where manual labelling is prohibitively expensive. However, their detection latency…

Reinforcement learning with verifiable rewards (RLVR) and Rubrics as Rewards (RaR) have driven strong gains in domains with clear correctness signals and even in subjective domains by synthesizing evaluation criteria from ideal reference…

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose…

Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…

Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes. Theproblem can be seen as learning a function which general-izes well to…

Robotic manipulation policies often fail to generalize because they must simultaneously learn where to attend, what actions to take, and how to execute them. We argue that high-level reasoning about where and what can be offloaded to…

The effectiveness of one-shot voice conversion (VC) decreases in real-world scenarios where reference speeches, which are often sourced from the internet, contain various disturbances like background noise. To address this issue, we…

Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples…

Zero-shot graph embedding is a major challenge for supervised graph learning. Although a recent method RECT has shown promising performance, its working mechanisms are not clear and still needs lots of training data. In this paper, we give…

Referring expression comprehension (REC) and segmentation (RES) are two highly-related tasks, which both aim at identifying the referent according to a natural language expression. In this paper, we propose a novel Multi-task Collaborative…